[PATCH 2/2] Add support for DW_TAG_GNU_annotation

[Vineet Gupta <vineet.gupta@linux.dev>]

gcc 16 was first release to support DW_TAG_GNU_annotation and this patch
enables the same in pahole. Bulk of changes are in dwarf_loader but
btf_encoder also gains support with minimal changes.

GCC encodes btf_type_tag and btf_decl_tag annotations differently from
LLVM. While LLVM uses DW_TAG_LLVM_annotation (0x6000) as child DIEs,
GCC uses DW_TAG_GNU_annotation (0x6001) as standalone sibling DIEs
referenced via DW_AT_GNU_annotation (0x2139) attributes, with chaining
through the same attribute on annotation DIEs themselves.

Handle both encoding styles:

For btf_type_tag (pointer annotations):
- Recognize DW_TAG_GNU_annotation alongside DW_TAG_LLVM_annotation in
  child annotation scanning.
- Follow DW_AT_GNU_annotation attribute chains on pointer types for
  GCC-style btf_type_tag resolution, with cycle detection.
- Normalize DW_TAG_GNU_annotation to DW_TAG_LLVM_annotation in the
  internal representation so downstream code works unchanged.

For btf_decl_tag (function/struct/member annotations):
- Add add_gnu_annotation_chain() to follow DW_AT_GNU_annotation
  attribute chains on function, struct, and member DIEs.
- GCC puts DW_AT_GNU_annotation on the function/struct DIE itself
  (not as child DIEs), referencing sibling annotation DIEs that chain
  via the same attribute.

Also:
- Silently skip standalone DW_TAG_GNU_annotation DIEs at CU level.
- Update pfunct-btf-decl-tags.sh test to use GCC 16+ when available and
  now passes.

Signed-off-by: Vineet Gupta <vineet.gupta@linux.dev>
---
 btf_encoder.c                 |   1 +
 dutil.h                       |   8 +++
 dwarf_loader.c                | 129 +++++++++++++++++++++++++++++-----
 dwarves.h                     |   3 +-
 dwarves_fprintf.c             |   8 ++-
 tests/pfunct-btf-decl-tags.sh |  32 ++++++---
 6 files changed, 152 insertions(+), 29 deletions(-)

diff --git a/btf_encoder.c b/btf_encoder.c
index 633bc6162ce0..d5af706d7638 100644
--- a/btf_encoder.c
+++ b/btf_encoder.c
@@ -1831,6 +1831,7 @@ static int btf_encoder__encode_tag(struct btf_encoder *encoder, struct tag *tag,
 		name = namespace__name(tag__namespace(tag));
 		return btf_encoder__add_ref_type(encoder, BTF_KIND_TYPEDEF, ref_type_id, name, false);
 	case DW_TAG_LLVM_annotation:
+	case DW_TAG_GNU_annotation:
 		name = tag__btf_type_tag(tag)->value;
 		return btf_encoder__add_ref_type(encoder, BTF_KIND_TYPE_TAG, ref_type_id, name, false);
 	case DW_TAG_structure_type:
diff --git a/dutil.h b/dutil.h
index ff78aa6dfd10..abe0e62b412f 100644
--- a/dutil.h
+++ b/dutil.h
@@ -35,6 +35,14 @@
 #define DW_TAG_LLVM_annotation 0x6000
 #endif
 
+#ifndef DW_TAG_GNU_annotation
+#define DW_TAG_GNU_annotation 0x6001
+#endif
+
+#ifndef DW_AT_GNU_annotation
+#define DW_AT_GNU_annotation 0x2139
+#endif
+
 static inline __attribute__((const)) bool is_power_of_2(unsigned long n)
 {
         return (n != 0 && ((n & (n - 1)) == 0));
diff --git a/dwarf_loader.c b/dwarf_loader.c
index 365cc24e212d..b34fbed8b670 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -908,6 +908,12 @@ static int tag__recode_dwarf_bitfield(struct tag *tag, struct cu *cu, uint16_t b
 	return -ENOMEM;
 }
 
+static bool die__tag_is_annotation(Dwarf_Die *die)
+{
+	unsigned int tag = dwarf_tag(die);
+	return tag == DW_TAG_LLVM_annotation || tag == DW_TAG_GNU_annotation;
+}
+
 static int add_llvm_annotation(Dwarf_Die *die, int component_idx, struct conf_load *conf,
 			       struct list_head *head)
 {
@@ -943,7 +949,7 @@ static int add_child_llvm_annotations(Dwarf_Die *die, int component_idx,
 
 	die = &child;
 	do {
-		if (dwarf_tag(die) == DW_TAG_LLVM_annotation) {
+		if (die__tag_is_annotation(die)) {
 			ret = add_llvm_annotation(die, component_idx, conf, head);
 			if (ret)
 				return ret;
@@ -953,6 +959,32 @@ static int add_child_llvm_annotations(Dwarf_Die *die, int component_idx,
 	return 0;
 }
 
+static int add_gnu_annotation_chain(Dwarf_Die *die, int component_idx,
+				    struct conf_load *conf, struct list_head *head)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Die annot_die;
+
+	if (dwarf_attr(die, DW_AT_GNU_annotation, &attr) == NULL ||
+	    dwarf_formref_die(&attr, &annot_die) == NULL)
+		return 0;
+
+	for (;;) {
+		if (dwarf_tag(&annot_die) != DW_TAG_GNU_annotation)
+			break;
+
+		int ret = add_llvm_annotation(&annot_die, component_idx, conf, head);
+		if (ret)
+			return ret;
+
+		if (dwarf_attr(&annot_die, DW_AT_GNU_annotation, &attr) == NULL ||
+		    dwarf_formref_die(&attr, &annot_die) == NULL)
+			break;
+	}
+
+	return 0;
+}
+
 int class_member__dwarf_recode_bitfield(struct class_member *member,
 					struct cu *cu)
 {
@@ -1596,6 +1628,8 @@ static struct btf_type_tag_type *die__create_new_btf_type_tag_type(Dwarf_Die *di
 		return NULL;
 
 	tag__init(&tag->tag, cu, die);
+	/* Normalize DW_TAG_GNU_annotation to DW_TAG_LLVM_annotation internally */
+	tag->tag.tag = DW_TAG_LLVM_annotation;
 	tag->value = attr_string(die, DW_AT_const_value, conf);
 	return tag;
 }
@@ -1635,26 +1669,65 @@ static struct tag *die__create_new_pointer_tag(Dwarf_Die *die, struct cu *cu,
 	Dwarf_Die *cdie, child;
 	const char *name;
 
-	/* If no child tags or skipping btf_type_tag encoding, just create a new tag
-	 * and return
-	 */
-	if (!dwarf_haschildren(die) || dwarf_child(die, &child) != 0 ||
-	    conf->skip_encoding_btf_type_tag)
+	if (conf->skip_encoding_btf_type_tag)
 		return tag__new(die, cu);
 
-	/* Otherwise, check DW_TAG_LLVM_annotation child tags */
-	cdie = &child;
-	do {
-		if (dwarf_tag(cdie) != DW_TAG_LLVM_annotation)
-			continue;
+	/* Check for LLVM-style child annotation tags */
+	if (dwarf_haschildren(die) && dwarf_child(die, &child) == 0) {
+		cdie = &child;
+		do {
+			if (!die__tag_is_annotation(cdie))
+				continue;
 
-		name = attr_string(cdie, DW_AT_name, conf);
-		if (strcmp(name, "btf_type_tag") != 0)
-			continue;
+			name = attr_string(cdie, DW_AT_name, conf);
+			if (strcmp(name, "btf_type_tag") != 0)
+				continue;
 
-		if (die__add_btf_type_tag(&tag, die, cdie, cu, conf))
-			return NULL;
-	} while (dwarf_siblingof(cdie, cdie) == 0);
+			if (die__add_btf_type_tag(&tag, die, cdie, cu, conf))
+				return NULL;
+		} while (dwarf_siblingof(cdie, cdie) == 0);
+	}
+
+	/* Check for GCC-style DW_AT_GNU_annotation attribute */
+	if (tag == NULL) {
+		Dwarf_Attribute attr;
+		Dwarf_Die annot_die;
+		Dwarf_Off visited[256];
+		int nr_visited = 0;
+
+		if (dwarf_attr(die, DW_AT_GNU_annotation, &attr) != NULL &&
+		    dwarf_formref_die(&attr, &annot_die) != NULL) {
+			for (;;) {
+				Dwarf_Off off = dwarf_dieoffset(&annot_die);
+				bool cycle = false;
+				int i;
+
+				for (i = 0; i < nr_visited; i++) {
+					if (visited[i] == off) {
+						cycle = true;
+						break;
+					}
+				}
+				if (cycle || nr_visited >= (int)ARRAY_SIZE(visited))
+					break;
+				visited[nr_visited++] = off;
+
+				if (dwarf_tag(&annot_die) != DW_TAG_GNU_annotation)
+					break;
+
+				name = attr_string(&annot_die, DW_AT_name, conf);
+				if (strcmp(name, "btf_type_tag") != 0)
+					break;
+
+				if (die__add_btf_type_tag(&tag, die, &annot_die, cu, conf))
+					return NULL;
+
+				if (dwarf_attr(&annot_die, DW_AT_GNU_annotation, &attr) == NULL ||
+				    dwarf_formref_die(&attr, &annot_die) == NULL)
+					break;
+			}
+		}
+	}
 
 	return tag ? &tag->tag : tag__new(die, cu);
 }
@@ -1684,6 +1757,12 @@ static struct tag *die__create_new_class(Dwarf_Die *die, struct cu *cu, struct c
 		}
 	}
 
+	if (class != NULL &&
+	    add_gnu_annotation_chain(die, -1, conf, &class->type.namespace.annots) != 0) {
+		class__delete(class, cu);
+		class = NULL;
+	}
+
 	return class ? &class->type.namespace.tag : NULL;
 }
 
@@ -2045,10 +2124,13 @@ static int die__process_class(Dwarf_Die *die, struct type *class,
 			cu__hash(cu, &member->tag);
 			if (add_child_llvm_annotations(die, member_idx, conf, &class->namespace.annots))
 				return -ENOMEM;
+			if (add_gnu_annotation_chain(die, member_idx, conf, &class->namespace.annots))
+				return -ENOMEM;
 			member_idx++;
 		}
 			continue;
 		case DW_TAG_LLVM_annotation:
+		case DW_TAG_GNU_annotation:
 			if (add_llvm_annotation(die, -1, conf, &class->namespace.annots))
 				return -ENOMEM;
 			continue;
@@ -2354,6 +2436,7 @@ static int die__process_function(Dwarf_Die *die, struct ftype *ftype,
 				goto out_enomem;
 			continue;
 		case DW_TAG_LLVM_annotation:
+		case DW_TAG_GNU_annotation:
 			if (add_llvm_annotation(die, -1, conf, &(tag__function(&ftype->tag)->annots)))
 				goto out_enomem;
 			continue;
@@ -2402,6 +2485,12 @@ static struct tag *die__create_new_function(Dwarf_Die *die, struct cu *cu, struc
 		function = NULL;
 	}
 
+	if (function != NULL &&
+	    add_gnu_annotation_chain(die, -1, conf, &function->annots) != 0) {
+		function__delete(function, cu);
+		function = NULL;
+	}
+
 	return function ? &function->proto.tag : NULL;
 }
 
@@ -2463,6 +2552,9 @@ static struct tag *__die__process_tag(Dwarf_Die *die, struct cu *cu,
 		 */
 		tag = &unsupported_tag;
 		break;
+	case DW_TAG_GNU_annotation:
+		tag = &unsupported_tag;
+		break;
 	case DW_TAG_label:
 		if (conf->ignore_labels)
 			tag = &unsupported_tag; // callers will assume conf->ignore_labels is true
@@ -2488,7 +2580,8 @@ static int die__process_unit(Dwarf_Die *die, struct cu *cu, struct conf_load *co
 			// XXX special case DW_TAG_dwarf_procedure, appears when looking at a recent ~/bin/perf
 			// Investigate later how to properly support this...
 			if (dwarf_tag(die) != DW_TAG_dwarf_procedure &&
-			    dwarf_tag(die) != DW_TAG_label) // conf->ignore_labels == true, see die__process_tag()
+			    dwarf_tag(die) != DW_TAG_label && // conf->ignore_labels == true, see die__process_tag()
+			    dwarf_tag(die) != DW_TAG_GNU_annotation)
 				tag__print_not_supported(die);
 			continue;
 		}
diff --git a/dwarves.h b/dwarves.h
index 5ec16e750e83..42b8e39aa2dd 100644
--- a/dwarves.h
+++ b/dwarves.h
@@ -670,7 +670,8 @@ static inline int tag__is_tag_type(const struct tag *tag)
 	       tag->tag == DW_TAG_volatile_type ||
 	       tag->tag == DW_TAG_atomic_type ||
 	       tag->tag == DW_TAG_unspecified_type ||
-	       tag->tag == DW_TAG_LLVM_annotation;
+	       tag->tag == DW_TAG_LLVM_annotation ||
+	       tag->tag == DW_TAG_GNU_annotation;
 }
 
 static inline const char *tag__decl_file(const struct tag *tag,
diff --git a/dwarves_fprintf.c b/dwarves_fprintf.c
index 1ec478c2a027..a514d7e98923 100644
--- a/dwarves_fprintf.c
+++ b/dwarves_fprintf.c
@@ -140,6 +140,8 @@ const char *dwarf_tag_name(const uint32_t tag)
 		return dwarf_gnu_tag_names[tag - DW_TAG_MIPS_loop];
 	else if (tag == DW_TAG_LLVM_annotation)
 		return "LLVM_annotation";
+	else if (tag == DW_TAG_GNU_annotation)
+		return "GNU_annotation";
 	return "INVALID";
 }
 
@@ -658,6 +660,7 @@ static const char *__tag__name(const struct tag *tag, const struct cu *cu,
 		snprintf(bf, len, "%s", variable__name(tag__variable(tag)));
 		break;
 	case DW_TAG_LLVM_annotation:
+	case DW_TAG_GNU_annotation:
 		type = cu__type(cu, tag->type);
 		if (type == NULL && tag->type != 0)
 			tag__id_not_found_snprintf(bf, len, tag->type);
@@ -731,7 +734,7 @@ static type_id_t skip_llvm_annotations(const struct cu *cu, type_id_t id)
 		if (id == 0)
 			break;
 		type = cu__type(cu, id);
-		if (type == NULL || type->tag != DW_TAG_LLVM_annotation || type->type == id)
+		if (type == NULL || (type->tag != DW_TAG_LLVM_annotation && type->tag != DW_TAG_GNU_annotation) || type->type == id)
 			break;
 		id = type->type;
 	}
@@ -936,7 +939,8 @@ print_modifier: {
 		else
 			printed += enumeration__fprintf(type, &tconf, fp);
 		break;
-	case DW_TAG_LLVM_annotation: {
+	case DW_TAG_LLVM_annotation:
+	case DW_TAG_GNU_annotation: {
 		struct tag *ttype = cu__type(cu, type->type);
 		if (ttype) {
 			type = ttype;
diff --git a/tests/pfunct-btf-decl-tags.sh b/tests/pfunct-btf-decl-tags.sh
index 35884b4e8687..5fdddc09f179 100755
--- a/tests/pfunct-btf-decl-tags.sh
+++ b/tests/pfunct-btf-decl-tags.sh
@@ -13,17 +13,21 @@ trap cleanup EXIT
 
 title_log "Check that pfunct can print btf_decl_tags read from BTF."
 
-# gcc now also supports decl tags as of gcc commit 43dcea48b8c,
-# in upstream version 16.
-# UPTODO: add a check here for that.
+# gcc 16+ supports decl tags via DW_TAG_GNU_annotation (gcc commit ac7027f180b).
+# Use gcc if available and version >= 16, otherwise fall back to clang.
 
+GCC=${GCC:-gcc}
 CLANG=${CLANG:-clang}
-if ! command -v $CLANG > /dev/null; then
-	error_log "Need clang for test $0"
-	test_fail
+
+use_gcc=0
+if command -v $GCC > /dev/null; then
+	gcc_ver=$($GCC -dumpversion 2>/dev/null | cut -d. -f1)
+	if [ "$gcc_ver" -ge 16 ] 2>/dev/null; then
+		use_gcc=1
+	fi
 fi
 
-(cat <<EOF
+src=$(cat <<EOF
 #define __tag(x) __attribute__((btf_decl_tag(#x)))
 
 __tag(a) __tag(b) __tag(c) void foo(void) {}
@@ -31,7 +35,19 @@ __tag(a) __tag(b)          void bar(void) {}
 __tag(a)                   void buz(void) {}
 
 EOF
-) | $CLANG --target=bpf -c -g -x c -o $tmpobj -
+)
+
+if [ "$use_gcc" -eq 1 ]; then
+	info_log "Using $GCC (version $gcc_ver) for btf_decl_tag test"
+	echo "$src" | $GCC -c -g -x c -o $tmpobj - 2>/dev/null
+	pahole -J $tmpobj 2>/dev/null
+elif command -v $CLANG > /dev/null; then
+	info_log "Using $CLANG for btf_decl_tag test"
+	echo "$src" | $CLANG --target=bpf -c -g -x c -o $tmpobj -
+else
+	error_log "Need gcc >= 16 or clang for test $0"
+	test_fail
+fi
 
 # tags order is not guaranteed
 sort_tags=$(cat <<EOF
-- 
2.54.0